edufour/RamanClassifier
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

First data dump and metadata handling

Browse Source
This commit is contained in:
edufour
2024-02-26 19:16:07 +01:00
parent f466cd0a2d
commit d7ec6835c8
32 changed files with 712983 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
data_raw/metadata_aggregator.py Normal file
View File

@@ -0,0 +1,21 @@
import os
import pandas as pd
df = pd.DataFrame([i for i in os.listdir() if i.endswith(".txt")], columns=["file"])
df["strain"] = df.apply(lambda x: x.file[:4].upper(), axis=1)
df["replica"] = df.apply(lambda x: x.file.split("_")[0][-1], axis=1)
df["replica"] = df.apply(lambda x: int(x.replica) if x.replica.isnumeric() else None, axis=1)
df["phase"] = df.apply(lambda x: x.file.split("_")[0].replace("SampleSpectra", "")[4:-1 if x.replica is not None else None].casefold(), axis=1)
df["objective"] = df.apply(lambda x: int(x.file.split("_")[1].replace("x", "")), axis=1)
df["substrate"] = df.apply(lambda x: x.file.split("_")[4].casefold(), axis=1)
df["laser_power[%]"] = df.apply(lambda x: int(x.file.split("_")[5].replace("percent", "")), axis=1)
df["grating"] = df.apply(lambda x: int(x.file.split("_")[6].replace("gr", "")), axis=1)
df["exposition[sec]"] = df.apply(lambda x: int(x.file.split("_")[7].replace("sec", "")), axis=1)
df["confocalhigh"] = df.apply(lambda x: x.file.split("_")[8] == "confocalhigh", axis=1)
df["accumulations"] = df.apply(lambda x: int(x.file.split("_")[9].replace("."," ").replace("(", " ").split()[0].replace("accu", "")), axis=1)
df.set_index("file", inplace=True)
df.to_csv("metadata.csv")
print(df)